Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jeonnoin-alt/Eureka --skill figure-designgit clone --depth 1 https://github.com/jeonnoin-alt/EurekaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jeonnoin-alt/eureka/figure-design)<a href="https://agentmods.dev/skills/jeonnoin-alt/eureka/figure-design"><img src="https://agentmods.dev/badge/skills/jeonnoin-alt/eureka/figure-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jeonnoin-alt/eureka/figure-design"><img src="https://agentmods.dev/badge/skills/jeonnoin-alt/eureka/figure-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.05049 |
| Opus 5 | $0.00037 | $0.02524 |
| Sonnet 5 | $0.00015 | $0.01010 |
| Haiku 4.5 | $0.00007 | $0.00505 |
Grade A, and why
figure-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure Design
Overview
Guide the creation of a research figure with the same discipline Eureka applies to everything else: gates before rendering, iron laws that do not bend, a hard prohibition on chart junk, and a fresh-eyes subagent review after every figure. A figure is an argument — every pixel either advances it or distracts from it.
Core principle: A peer reviewer spends 3 seconds on a figure before forming an opinion. Those 3 seconds decide whether they read the caption, the text, or the paper at all.
The Iron Law
NO FIGURE WITHOUT A GENERATING SCRIPT.
NO SUBMISSION WITHOUT COLORBLIND-SAFE PALETTE.
NO DEFAULT MATPLOTLIB STYLE IN A TOP-JOURNAL SUBMISSION.
Writing a figure means writing a script that produces it deterministically. Picking a palette means picking one that 8% of male readers can still decode. Setting a style means setting it once at the top of the script and never editing the output manually.
When to Use
Use this skill when:
- The user says "make a figure", "draw fig X", "plot the results", "update the brain map", "the figure looks wrong"
- A Results section is being written and a figure is needed
- An existing figure failed reviewer feedback or journal submission
- A multi-panel composite figure is being assembled
Do NOT use when:
- The user is doing pure data analysis with no figure output (no skill needed)
- The user wants to verify figure integrity post-hoc (use
eureka:claims-auditPart B) - The user is writing a manuscript section (use
eureka:manuscript-writing)
Checklist
You MUST create a task for each of these and complete them in order:
- Determine figure purpose — ask the user: what argument does this figure advance? One sentence.
- Identify target journal — ask the user, or check
CLAUDE.md/ the manuscript. Different journals have different column widths, fonts, formats. - Select chart type — match the purpose to a chart type (see Chart Type Selection Gate below)
- Set global style ONCE —
apply_paper_style()-equivalent at the top of the script (font family, TrueType embedding, DPI, spine style) - Render the figure — write the script; run it; inspect the output
- Apply iron laws — typography, color, layout, export format (see Iron Laws below)
- Inline self-check — run through the Red Flags list
- Dispatch
figure-reviewersubagent — per figure, after the inline check passes - Act on feedback — fix issues; re-render; re-dispatch until approved
- Commit script + output — both the
.py/.Rand the.pdf/.svggo to git
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 314 lines · 75 tokens per session scan A 2ae48a0c8031
figure-design is a skill published in the GitHub repository jeonnoin-alt/Eureka (2 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 5,049 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and…
presentation-design
Designs slide decks and one-pagers that carry an argument rather than decorate one — deck structure, headlines that state the takeaway, charts that make a single point, and the different rules board decks and conference talks follow. Use this to build or fix a pitch deck, board deck, or conference talk, to design a…
ux-product-auditor
Audits a website, app, onboarding flow, or design for usability, conversion, and product problems, tying every finding to a business outcome and a severity. Use this to review an interface, diagnose low conversion or activation, find where users drop off, get structured product feedback, or decide which UX fixes to…
design-styles
Applies a deliberate visual direction to an interface — minimalist editorial, industrial utilitarian, or high-polish commercial — each with its own type scale, palette behavior, surface treatment, and motion. Use this when a product needs a point of view rather than defaults, when choosing between visual directions…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…